© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 91797
    Prev
    Next
    INDEX
    Explanations

    css prefixes like -webkit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    &apos
    -0.11
    loat
    -0.10
    inspace
    -0.09
    <|fim_suffix|>
    -0.09
     Bac
    -0.09
    &eacute
    -0.08
    serie
    -0.08
     homo
    -0.08
     hitch
    -0.08
    Sizer
    -0.08
    POSITIVE LOGITS
    ï¸ı
    0.11
     Chronicles
    0.09
     Fant
    0.09
     Hanna
    0.09
     Guar
    0.09
     incur
    0.09
     Cong
    0.09
     Anal
    0.09
     Kash
    0.09
    Internet
    0.09
    Activations Density 0.001%

    No Known Activations